import re
def sort_html_file(input_file_name, output_file_name, phrase):
try:
with open(input_file_name, 'r', encoding='utf-8', errors='ignore') as f:
html = f.read()
print("HTML loaded successfully")
# Find all links and descriptions
links_and_descriptions = re.findall(r'.*?<\/li>', html, re.DOTALL)
print("Links and descriptions found:", len(links_and_descriptions))
# Extract link and description from each item
extracted_links_and_descriptions = []
for item in links_and_descriptions:
match = re.search(r'href=[\'"]([^\'"]+)', item, re.DOTALL)
if match:
link = match.group(1)
match = re.search(r'>[^<]+?<\/a>', item)
if match:
link_text = match.group(0)[1:-4]
description = re.sub(r'<.*?>', '', item).strip().split('-', 1)[1].strip()
title_text_match = re.search(r'title=[\'"]([^\'"]+)[\'"]', item)
if title_text_match:
title_text = title_text_match.group(1)
else:
title_match = re.search(r'(.*?)<\/a>', item)
if title_text_match:
title_text = title_text_match.group(0)[1:-4]
else:
title_text = link_text
title_match = re.search(r'.*?(.*?)<\/a>', item, re.DOTALL)
if title_match:
title = title_match.group(1)
else:
title = link_text
extracted_links_and_descriptions.append((link, link_text, title_text, description, title))
# Add the print code here
for link, link_text, title_text, title, description in extracted_links_and_descriptions:
''' print("Link:", link)
print("Link Text:", link_text)
print("Title Text:", title_text)
print("Title:", title)
print("Description:", description)
print("------------------------") '''
print("Extracted links and descriptions:", len(extracted_links_and_descriptions))
# Sort links and descriptions based on the presence of the phrase
phrase_links_and_descriptions = [x for x in extracted_links_and_descriptions if phrase.lower() in x[2].lower()]
other_links_and_descriptions = [x for x in extracted_links_and_descriptions if phrase.lower() not in x[2].lower()]
sorted_phrase_links_and_descriptions = sorted(phrase_links_and_descriptions, key=lambda x: x[2].lower().find(phrase.lower()))
sorted_other_links_and_descriptions = sorted(other_links_and_descriptions, key=lambda x: x[2].lower().find(phrase.lower()))
sorted_links_and_descriptions = []
words = phrase.split()
added_descriptions = set()
for link, link_text, title_text, description, title in sorted_phrase_links_and_descriptions + sorted_other_links_and_descriptions:
if phrase.lower() in description.lower():
description = re.sub(r'(' + re.escape(phrase) + r')', r'\1', description, flags=re.IGNORECASE)
for word in words:
if phrase.lower() not in description.lower():
description = re.sub(r'(' + re.escape(word) + r')', r'\1', description, flags=re.IGNORECASE)
description_words = description.split()
description_hash = tuple(sorted(description_words[:9])) # Use the first 9 words as a hash
if description_hash not in added_descriptions:
sorted_links_and_descriptions.append((link, link_text, title_text, description, title))
added_descriptions.add(description_hash)
print("Links and descriptions sorted")
# Create the sorted HTML
sorted_html = 'Search Results
'
sorted_html = 'Search Results
'
sorted_html += ''
sorted_html += ''
sorted_html += ''
sorted_html += ''
sorted_html += ''
sorted_html += ''
sorted_html += ''
for link, link_text, title_text, description, title in sorted_links_and_descriptions[:10]:
sorted_html += f'- {link_text} - {description}
'
sorted_html += '
'
print("Sorted HTML created")
# Save the sorted HTML to the output file
with open(output_file_name, 'w', encoding='utf-8', errors='ignore') as f:
f.write(sorted_html)
print("Sorted HTML saved to output file as",output_file_name)
print(title)
except Exception as e:
print("An error occurred:", str(e))
# Usage
input_file_name ='search_multiple_words.html'
output_file_name ='adhyatm-kya-hai.html'
phrase = 'अध्यात्म क्या है'
# sort_html_file(input_file_name, output_file_name, phrase)